Hacker News new | ask | show | jobs
by MaBu 2779 days ago
It definitely doesn't use state of the art TTS. It sounds similar to MBrola english voice. There is google's [Wavenet](https://deepmind.com/blog/wavenet-generative-model-raw-audio...) and even chinese Baidus [Clarinet](https://clarinet-demo.github.io/) which are much better.
1 comments

Cheers - yep google's especially sounds much more realistic. Obviously still awhile to go before a user would be tricked into thinking it's a real voice.